CN109446483B - Machine appraisal method for objective questions containing subjective information - Google Patents
Machine appraisal method for objective questions containing subjective information Download PDFInfo
- Publication number
- CN109446483B CN109446483B CN201811160860.6A CN201811160860A CN109446483B CN 109446483 B CN109446483 B CN 109446483B CN 201811160860 A CN201811160860 A CN 201811160860A CN 109446483 B CN109446483 B CN 109446483B
- Authority
- CN
- China
- Prior art keywords
- score
- objective
- question
- confidence level
- machine
- Prior art date
- Legal status (The legal status is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the status listed.)
- Active
Links
- 238000000034 method Methods 0.000 title claims abstract description 28
- 238000004364 calculation method Methods 0.000 claims description 4
- 238000012797 qualification Methods 0.000 claims 5
- 238000012360 testing method Methods 0.000 abstract description 10
- 230000008901 benefit Effects 0.000 description 4
- 238000011156 evaluation Methods 0.000 description 4
- 230000009286 beneficial effect Effects 0.000 description 1
- 230000000694 effects Effects 0.000 description 1
- 238000013100 final test Methods 0.000 description 1
- 230000010365 information processing Effects 0.000 description 1
- 230000002452 interceptive effect Effects 0.000 description 1
- 238000003672 processing method Methods 0.000 description 1
- 238000013077 scoring method Methods 0.000 description 1
- 238000006467 substitution reaction Methods 0.000 description 1
Images
Classifications
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F17/00—Digital computing or data processing equipment or methods, specially adapted for specific functions
- G06F17/10—Complex mathematical operations
- G06F17/18—Complex mathematical operations for evaluating statistical data, e.g. average values, frequency distributions, probability functions, regression analysis
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06Q—INFORMATION AND COMMUNICATION TECHNOLOGY [ICT] SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES; SYSTEMS OR METHODS SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES, NOT OTHERWISE PROVIDED FOR
- G06Q50/00—Information and communication technology [ICT] specially adapted for implementation of business processes of specific business sectors, e.g. utilities or tourism
- G06Q50/10—Services
- G06Q50/20—Education
- G06Q50/205—Education administration or guidance
Landscapes
- Engineering & Computer Science (AREA)
- Physics & Mathematics (AREA)
- Business, Economics & Management (AREA)
- General Physics & Mathematics (AREA)
- Data Mining & Analysis (AREA)
- Theoretical Computer Science (AREA)
- Tourism & Hospitality (AREA)
- Mathematical Physics (AREA)
- Computational Mathematics (AREA)
- Mathematical Analysis (AREA)
- Mathematical Optimization (AREA)
- Strategic Management (AREA)
- Educational Technology (AREA)
- Pure & Applied Mathematics (AREA)
- Educational Administration (AREA)
- Bioinformatics & Computational Biology (AREA)
- Life Sciences & Earth Sciences (AREA)
- Software Systems (AREA)
- General Engineering & Computer Science (AREA)
- Evolutionary Biology (AREA)
- Bioinformatics & Cheminformatics (AREA)
- Algebra (AREA)
- Probability & Statistics with Applications (AREA)
- Operations Research (AREA)
- Databases & Information Systems (AREA)
- Health & Medical Sciences (AREA)
- Economics (AREA)
- General Health & Medical Sciences (AREA)
- Human Resources & Organizations (AREA)
- Marketing (AREA)
- Primary Health Care (AREA)
- General Business, Economics & Management (AREA)
- Electrically Operated Instructional Devices (AREA)
Abstract
The invention discloses a machine appraising method for objective questions containing subjective information, which is suitable for a computer system and mainly comprises the following steps: s1, adding confidence level options on the basis of the traditional objective questions, and giving different weights to the confidence level options; s2, judging whether the answer to the objective question is correct or not; s3, recognizing the confidence level option and determining an alpha value; s4, calculating a score according to the title score and the confidence coefficient weight; and S5, outputting the final score. The invention generally introduces subjective and objective combination of confidence degree options in a machine appraisal paper with a scoring principle, not only maintains the Boolean characteristic of objective questions, ensures accurate and rapid appraisal, but also considers the test of the subjective thinking process of an answerer, forms the process thinking of the answerer into quantitative indexes, enriches the connotation of the objective questions, and can more scientifically and accurately reflect the real conditions of the answerer.
Description
Technical Field
The invention relates to a computer information processing method, in particular to a computer appraising method based on Boolean operation.
Background
The objective questions are also called fixed response type test questions, which are to let examinees recognize correct answers from a plurality of answers drawn up in advance. The usual question type is a single-choice question structured to give 4 choices after the question, only 1 of which is the correct answer and the other 3, also known as the interfering answers, are all the wrong answers. The objective question proposition has the advantages of high flexibility, wide knowledge coverage, strong certainty of the examined contents, and the characteristic of ' not right, namely wrong ' Boolean ', and is easy to realize the automatic appraisal of the computer. Therefore, it is the most frequently used subject type in standardized examinations. The objective test questions are widely adopted in various examinations and teaching tests, and the proportion of the scores of the objective test questions in the examinations is usually greatly higher than that of the subjective test questions, so that the objective test questions in the final test result are decisive.
Although there are obvious advantages to this objective test, some drawbacks are also implied. For example, the thinking process of the student cannot be judged, only the thinking result can be obtained, and even if the student slightly knows the question, the student cannot obtain any score if the student fails to answer the question, and on the contrary, even if the student guesses the question, the student can obtain the full score. Therefore, although the traditional objective question test has simple and quick answering and evaluating processes and great advantages in the aspects of effectiveness and cost, a lot of subjective information can be lost, and the real condition of a tested person can be covered to a certain extent.
Disclosure of Invention
Aiming at the problems, the invention provides a machine appraising method for objective questions containing subjective information, which can more accurately identify and distinguish the subjective psychological conditions of testers during answering, each question answer needs to distinguish different conditions without being full, and the questions cannot be scored and also can be deducted when the questions are answered incorrectly. Therefore, the tester can be judged more comprehensively, and powerful help is provided for dynamically adjusting teaching difficulties and improving teaching effect, efficiency and benefit.
The technical scheme of the invention is realized as follows:
a machine-appraisal method for objective questions containing subjective information, the method being adapted for use with a computer system, comprising the steps of:
s1, adding confidence level options on the basis of the traditional objective questions, and giving different weights to the confidence level options;
s2, judging whether the answer to the objective question is correct, if correct, entering step S3, and if wrong, entering step S3';
s3, recognizing the confidence level options and determining an alpha value;
s4, calculating a score according to the title score and the confidence coefficient weight;
s3 ', determining whether the confidence level option is 100%, if yes, the process proceeds to S4', if no, the process proceeds to S4 ";
s4', calculating scores according to the item scores;
s4', introducing a negative adjustment item;
s4.1, calculating scores according to the title scores, the confidence coefficient weights and the user-defined negative adjustment item numerical values;
and S5, outputting the final score.
Further, the calculation formula of the calculated score is S ═ Sign | M | + Δ, where: s is the score, Sign is a Sign function, namely +/-1; the M is a module value, namely the topic score; α is a confidence value, i.e. a score weight; when the weight is 100%, the computer defaults delta to be zero, and in other cases, the delta is given by the computer according to a self-defined value of a question person, and the question person self-defines the delta of each question by a value not more than | M | according to the difficulty of each question and provides the delta to the computer through a list, and the delta is read by the computer in sequence during appraising.
Further, in step S4, Sign is +1, Δ is 0, and the score S is calculated as | M | × α.
Further, in step S4', Sign ═ 1, α ═ 1, and Δ ═ 0, the score S ═ M |.
Further, in step S4.1 ", Sign ═ 1, Δ ≠ 0 and Δ ≦ M |, the final score S ═ M | × + α + Δ, and S is defined to be ≦ 0, i.e., S > 0 is taken as S ═ 0.
Furthermore, the objective question options and the confidence level options are 4, and the confidence level options are specifically set as follows: a.100%, meaning 100% identifies the selected answer, with a weight α of 1; b.75%, meaning that 75% of the answers selected, the weight α is 0.75; c.50%, meaning that 50% identifies the selected answer, with a weight α of 0.50; d.25%, meaning that 25% identifies the selected answer, the weight α is 0.25.
The invention has the beneficial effects that: generally, the subjective and objective combination of confidence level options is introduced into a machine appraisal paper, so that the Boolean characteristic of an objective question is maintained, the accuracy and quickness of appraisal and reading are ensured, the test of the subjective thinking process of an answerer is considered, the process thinking of the answerer is formed into a quantitative index, the connotation of the objective question is enriched, and the real condition of the answerer can be reflected more scientifically and accurately.
Drawings
FIG. 1 is a flow chart of the evaluation method according to the present invention;
FIG. 2 is a schematic screenshot of a conventional objective question;
FIG. 3 is a schematic screenshot of an objective question including subjective confidence according to the present invention.
Detailed Description
The following detailed description of embodiments of the invention refers to the accompanying drawings:
as shown in fig. 1, a machine-appraising method for objective questions including subjective information, the method being applied to a computer system, includes the steps of:
s1, adding confidence level options on the basis of the traditional objective questions, and giving different weights to the confidence level options;
s2, judging whether the answer to the objective question is correct, if correct, entering step S3, and if wrong, entering step S3';
s3, recognizing the confidence level option and determining an alpha value;
s4, calculating a score according to the title score and the confidence coefficient weight;
s3 ', determining whether the confidence level option is 100%, if yes, the process proceeds to S4', if no, the process proceeds to S4 ";
s4', calculating a score according to the title score;
s4', introducing a negative adjustment item;
s4.1, calculating scores according to the topic scores, the confidence coefficient weights and the user-defined negative score adjustment item values;
and S5, outputting the final score.
Further, the calculation formula of the calculated score is S ═ Sign | M | + Δ, where: s is the score, Sign is a Sign function, namely +/-1; the M is a module value, namely the topic score; α is a confidence value, i.e. a score weight; when the weight is 100%, the computer defaults delta to be zero, and in other cases, the delta is given by the computer according to a self-defined value of a question person, and the question person self-defines the delta of each question by a value not more than | M | according to the difficulty of each question and provides the delta to the computer through a list, and the delta is read by the computer in sequence during appraising.
Further, in step S4, Sign is +1, Δ is 0, and the score S is calculated as | M | × α.
Further, in step S4', Sign ═ 1, α ═ 1, and Δ ═ 0, the score S ═ M |.
Further, in step S4.1 ", Sign ═ 1, Δ ≠ 0 and Δ ≦ M |, the final score S — | M | + α + Δ, and S ≦ 0 is defined, i.e., when S > 0, S ═ 0 is taken.
Furthermore, the objective question options and the confidence level options are 4, and the confidence level options are specifically set as follows: a.100%, meaning 100% identifies the selected answer, with a weight α of 1; b.75%, meaning that 75% of the answers selected, the weight α is 0.75; c.50%, meaning that 50% identifies the selected answer, with a weight α of 0.50; d.25%, meaning that 25% identifies the selected answer, the weight α is 0.25.
In the specific embodiment, firstly, 4 confidence level options are added on the basis of 4 options of the traditional objective choice question, the confidence level reflects the determination degree of the choice of the answer person subjectivity, and different confidence levels correspond to different weights. The specific confidence level options are: 100% means 100% identifies the selected answer, with a weight of 1; b. 75% means that 75% of the answers selected are considered, with a weight of 0.75; c. 50% means that 50% identifies the selected answer, with a weight of 0.50; d. 25% means that 25% identifies the selected answer, with a weight of 0.25.
And then, after adding the subjective confidence option, performing score evaluation by integrating the subjective weight and the objective answer result, wherein the algorithm formula is as follows: s ═ Sign | M | + Δ. Wherein: s is score; sign is a Sign function (i.e., ± 1); | M | is a module value (i.e., topic score); α is the confidence (i.e., the scoring weight); Δ is the offset (i.e., the negative fractional adjustment term). The judging steps are as follows:
(1) and judging whether the judgment is correct or incorrect. Similar to the traditional boolean objective question, Sign is +1 if the answerer selects the correct answer, and Sign is-1 if the answerer selects the wrong answer;
(2) and identifying a confidence option if the answer is correct. Sign +1, Δ 0, the algorithm is simplified as: s | M | ×;
(3) identifying confidence options in case of wrong answer:
if the wrong answer is selected with 100% confidence, Sign-1, α -1, and Δ -0, the algorithm is simplified to: s ═ M |;
if the wrong answer is selected under the condition of the rest confidence degrees, the negative partial adjustment term is delta, and the algorithm formula is simplified as follows: s ═ M |. α + Δ; where Δ ≦ M |, and S is defined as ≦ 0 (i.e., S ≦ 0 when S > 0).
And finally obtaining the evaluation scores comprising the subjective tendency degree of the students to the selected answers and the objective answer results of the students.
As shown in FIG. 2, it is an objective selection question of "automatic control principle" course. If the correct answer of the question is 'option A' and the score is 4, the traditional scoring method is to select the right and get 4 scores, and to select the wrong and not get the score. First add 4 confidence level options, a, b, c, d, and the improved topic information is shown in fig. 3. Then, judging whether the error is correct or not; sign is +1 if the answerer selects the correct answer (i.e., the a choice in the example question), and Sign is-1 if the wrong answer (i.e., the B, C, D choice in the example question) is selected. Further, identifying a confidence option under the condition that the answer is correct; for example, when the a option is selected after the a option is selected, the score S (+4) × 1 ═ 4 is given; if the option b is selected, the score is S (+4) multiplied by 0.75 to 3; by analogy, different scores are obtained by different subjective information on the premise of correct answers. Further, confidence options are identified in the event the answer is incorrect. If the wrong answer is selected with 100% confidence, such as B (a), C (a), D (a). Sign-1, α -1, Δ -0, the algorithm is simplified to: s ═ M |, then score S ═ 4| ═ 4 score; if the wrong answer is selected under the condition of the rest confidence degrees, such as B (c), C (d), D (b) and the like, the negative adjustment term delta is not equal to 0, and the algorithm formula is simplified as follows: s ═ M |. α + Δ, where Δ ≦ M |, and S is defined to be ≦ 0 (i.e., S ═ 0 when S > 0). In the example, if the option b (c) is selected, the score S is (-4) × 0.5+2.5 ≠ 0.5 ≠ 0; selecting option D (b), and scoring S (-4) × 0.75+2.5 ═ 0.5 point; and so on. And finally obtaining the evaluation score of the question.
The above description is only an embodiment of the present invention, but the scope of the present invention is not limited thereto, and any teacher or tester skilled in the art should be able to make equivalent substitutions or changes according to the technical solutions and their inventive concepts within the scope of the present invention.
Claims (6)
1. A machine appraisal method for objective questions including subjective information, the method adapted for use in a computer system, comprising the steps of:
s1, adding confidence level options on the basis of the traditional objective questions, and giving different weights to the confidence level options;
s2, judging whether the answer to the objective question is correct, if correct, entering step S3, and if wrong, entering step S3';
s3, recognizing the confidence level options and determining an alpha value;
s4, calculating a score according to the title score and the confidence coefficient weight;
s3 ', determining whether the confidence level option is 100%, if yes, the process proceeds to S4', if no, the process proceeds to S4 ";
s4', calculating a score according to the title score;
s4', introducing a negative adjustment item;
s4.1, calculating scores according to the topic scores, the confidence coefficient weights and the user-defined negative score adjustment item values;
and S5, outputting the final score.
2. The machine-qualification method of claim 1, wherein: the calculation formula adopted by the calculation score is S ═ Sign | M |. alpha + delta, wherein: s is the score, Sign is a Sign function, namely +/-1; the M is a module value, namely the topic score; alpha is a confidence value, namely a score weight; when the weight is 100%, the computer defaults delta to be zero, and in other cases, the delta is given by the computer according to a self-defined value of a question person, and the question person self-defines the delta of each question by a value not more than | M | according to the difficulty of each question and provides the delta to the computer through a list, and the delta is read by the computer in sequence during appraising.
3. The machine-qualification method of claim 2, wherein: in step S4, Sign +1 and Δ 0 are added, and a score S | M |. α is calculated.
4. The machine-qualification method of claim 2, wherein: in step S4', Sign ═ 1, α ═ 1, and Δ ═ 0, and the score S ═ M |.
5. The machine-qualification method of claim 2, wherein: in step S4.1 ", Sign ═ 1, Δ ≠ 0, and Δ ≦ M |, and the final score S ═ M | × + α + Δ is defined such that S is not more than 0, i.e., S > 0 is taken as S ═ 0.
6. The machine-qualification method of any of the preceding claims, wherein: the objective question options and the confidence level options are 4, and the confidence level options are specifically set as follows: a.100%, meaning 100% identifies the selected answer, with a weight α of 1; b.75%, meaning that 75% of the answers selected, the weight α is 0.75; c.50%, meaning that 50% identifies the selected answer, with a weight α of 0.50; d.25%, meaning that 25% identifies the selected answer, the weight α is 0.25.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201811160860.6A CN109446483B (en) | 2018-09-30 | 2018-09-30 | Machine appraisal method for objective questions containing subjective information |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201811160860.6A CN109446483B (en) | 2018-09-30 | 2018-09-30 | Machine appraisal method for objective questions containing subjective information |
Publications (2)
| Publication Number | Publication Date |
|---|---|
| CN109446483A CN109446483A (en) | 2019-03-08 |
| CN109446483B true CN109446483B (en) | 2022-09-30 |
Family
ID=65545943
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN201811160860.6A Active CN109446483B (en) | 2018-09-30 | 2018-09-30 | Machine appraisal method for objective questions containing subjective information |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN109446483B (en) |
Families Citing this family (3)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN111178770B (en) * | 2019-12-31 | 2023-11-10 | 安徽知学科技有限公司 | Answer data evaluation and learning image construction method, device and storage medium |
| CN112069815B (en) * | 2020-09-04 | 2023-01-17 | 平安科技（深圳）有限公司 | Answer selection method and device for idiom filling-in-blank question and computer equipment |
| CN112163093B (en) * | 2020-10-13 | 2022-04-12 | 杭州电子科技大学 | Electric power resident APP multi-question type questionnaire score classification method based on characteristic values |
Citations (4)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| JP2015022081A (en) * | 2013-07-17 | 2015-02-02 | 株式会社シーティーイー | Device and method for supporting memory learning |
| CN106611522A (en) * | 2015-10-27 | 2017-05-03 | 金陵科技学院 | Application of learning software system based on objective questions |
| WO2018094925A1 (en) * | 2016-11-22 | 2018-05-31 | 深圳市鹰硕技术有限公司 | Method and system for generating blank filling question and grading |
| CN108388895A (en) * | 2018-03-04 | 2018-08-10 | 南京理工大学 | A kind of paper answering card automatic processing method based on machine learning |
-
2018
- 2018-09-30 CN CN201811160860.6A patent/CN109446483B/en active Active
Patent Citations (4)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| JP2015022081A (en) * | 2013-07-17 | 2015-02-02 | 株式会社シーティーイー | Device and method for supporting memory learning |
| CN106611522A (en) * | 2015-10-27 | 2017-05-03 | 金陵科技学院 | Application of learning software system based on objective questions |
| WO2018094925A1 (en) * | 2016-11-22 | 2018-05-31 | 深圳市鹰硕技术有限公司 | Method and system for generating blank filling question and grading |
| CN108388895A (en) * | 2018-03-04 | 2018-08-10 | 南京理工大学 | A kind of paper answering card automatic processing method based on machine learning |
Non-Patent Citations (2)
| Title |
|---|
| 关于单项选择与多项选择题分值确定的探讨;陶应奇;《烟台师范学院学报(自然科学版)》;20020330(第01期);全文 * |
| 客观题和半客观题在信息技术总结性评价中的应用研究;曹书成等;《中国电化教育》;20060410(第04期);全文 * |
Also Published As
| Publication number | Publication date |
|---|---|
| CN109446483A (en) | 2019-03-08 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN109446483B (en) | Machine appraisal method for objective questions containing subjective information | |
| Gunderson et al. | Approximate number word knowledge before the cardinal principle | |
| US20110165550A1 (en) | Management system for online test assessment and method thereof | |
| Köhler et al. | Investigating mechanisms for missing responses in competence tests | |
| JP6190802B2 (en) | Computing to estimate the ability value of many candidates based on item response theory | |
| Alavi et al. | Differential item functioning analysis of high-stakes test in terms of gender: A Rasch model approach | |
| Prihoda et al. | Correcting for guessing increases validity in multiple‐choice examinations in an oral and maxillofacial pathology course | |
| Böttcher et al. | A data science-based approach for identifying counseling needs in first-year students | |
| RU2657228C1 (en) | Estimation method of competences of trainee at a given level | |
| CN111507872B (en) | Artificial intelligence-based accurate test difficulty classification method | |
| CN107845047B (en) | Dynamic scoring system, method and computer readable storage medium | |
| Alawiyah et al. | Analysis of misconception on solubility and solubility product constant (ksp) using three-tier multiple choice test | |
| CN111178770B (en) | Answer data evaluation and learning image construction method, device and storage medium | |
| RU2649550C2 (en) | Criteria-oriented testing system | |
| Lottridge et al. | Examining bias in automated scoring of reading comprehension items | |
| Was et al. | Improving Metacognition in a College Classroom: Does Enough Practice Work?. | |
| Buehler et al. | The Longitudinal Relation Between Language Abilities and Metacognitive Monitoring in Native and Non-native Speaking Children | |
| CN117094861B (en) | Language learning control test system | |
| Carr et al. | Reading readiness tests and grouping of first grade entrants | |
| Arıkan et al. | An example of empirical and model based methods for performance descriptors: English proficiency test | |
| Burfitt | Partial knowledge of understandings needed for proportional reasoning | |
| CN110349062B (en) | Artificial intelligence based pre-testing method | |
| Herosian et al. | Item Response Theory Analysis on Student Statistical Literacy Tests | |
| Eteng-Uket | Analysis of Socio-Economic Status and Gender Related Differential Item Functioning Using Item Response Theory Approach | |
| CN110765574B (en) | Method for constructing quantization relation between sample size and error elimination for online test |
Legal Events
| Date | Code | Title | Description |
|---|---|---|---|
| PB01 | Publication | ||
| PB01 | Publication | ||
| SE01 | Entry into force of request for substantive examination | ||
| SE01 | Entry into force of request for substantive examination | ||
| GR01 | Patent grant | ||
| GR01 | Patent grant |